© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 18-GEMMASCOPE-TRANSCODER-16K
    7. 7101
    Prev
    Next
    INDEX
    Explanations

    descriptions and reviews of local businesses or products

    oai_token-act-pair · gemini-2.0-flash

    independent

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AnimationsModule
    -0.93
     BorderRadius
    -0.89
     CreateTagHelper
    -0.88
    ⓧ
    -0.86
    DockStyle
    -0.75
    InjectAttribute
    -0.72
    StoreMessageInfo
    -0.69
     Réponses
    -0.69
     оригіналу
    -0.69
    elemField
    -0.69
    POSITIVE LOGITS
     independent
    0.47
     pop
    0.45
    thusi
    0.41
     small
    0.40
     senior
    0.40
    尖
    0.40
     Independent
    0.39
     Gilbert
    0.39
     a
    0.38
     pas
    0.38
    Activations Density 2.802%

    No Known Activations